Digital twins to fight against COVID-19 pandemic

This study is aimed to explore the anti-epidemic effect of artificial intelligence (AI) algorithms such as digital twins on the COVID-2019 (novel coronavirus disease 2019), so that the information security and prediction accuracy of epidemic prevention and control (P & C) in smart cities can be further improved. It addresses the problems in the current public affairs governance strategy for the outbreak of the COVID-2019 epidemic, and uses digital twins technology to map the epidemic P & C situation in the real space to the virtual space. Then, the blockchain technology and deep learning algorithms are introduced to construct a digital twins model of the COVID-2019 epidemic (the COVID-DT model) based on blockchain combined with BiLSTM (Bi-directional Long Short-Term Memory). In addition, performance of the constructed COVID-DT model is analyzed through simulation. Analysis of network data security transmission performance reveals that the constructed COVID-DT model shows a lower average delay, its data message delivery rate (DMDR) is basically stable at 80%, and the data message disclosure rate (DMDCR) is basically stable at about 10%. The analysis on network communication cost suggests that the cost of this study does not exceed 700 bytes, and the prediction error does not exceed 10%. Therefore, the COVID-DT model constructed shows high network security performance while ensuring low latency performance, enabling more efficient and accurate interaction of information, which can provide experimental basis for information security and development trends of epidemic P & C in smart cities. © 2022

Alpha Fusion Adversarial Attack Analysis Using Deep Learning

The deep learning model encompasses a powerful learning ability that integrates the feature extraction, and classification method to improve accuracy. Convolutional Neural Networks (CNN) perform well in machine learning and image processing tasks like segmentation, classification, detection, identification, etc. The CNN models are still sensitive to noise and attack. The smallest change in training images as in an adversarial attack can greatly decrease the accuracy of the CNN model. This paper presents an alpha fusion attack analysis and generates defense against adversarial attacks. The proposed work is divided into three phases: firstly, an MLSTM-based CNN classification model is developed for classifying COVID-CT images. Secondly, an alpha fusion attack is generated to fool the classification model. The alpha fusion attack is tested in the last phase on a modified LSTM-based CNN (CNN-MLSTM) model and other pre-trained models. The results of CNN models show that the accuracy of these models dropped greatly after the alpha-fusion attack. The highest F1 score before the attack was achieved is 97.45 And after the attack lowest F1 score recorded is 22%. Results elucidate the performance in terms of accuracy, precision, F1 score and Recall. © 2023 CRL Publishing. All rights reserved.

Customer prioritization for medical supply chain during COVID-19 pandemic

During COVID-19, the escalated demand for various pharmaceutical products with the existing production capacity of pharmaceutical companies has stirred the need to prioritize its customers in order to fulfill their demand. This study considers a two-echelon pharmaceutical supply chain considering various pharma-distributors as its suppliers and hospitals, pharmacies, and retail stores as its customers. Previous studies have generally considered a balanced situation in terms of supply and demand whereas this study considers a special situation of COVID-19 pandemic where demand exceeds supply Various criteria have been identified from the literature that influences the selection of customers. A questionnaire has been developed to collect primary data from pharmaceutical suppliers pertaining to customer-selection criteria. These criteria have been prioritized with respect to eigenvalues obtained from Principal Component Analysis and also validated with the experts' domain-related knowledge using Analytical Hierarchy Process. Profit potential appeared to be the most important criteria of customer selection followed by trust and service convenience brand loyalty, commitment, brand awareness, brand image, sustainable behavior, and risk. Subsequently, Multi Criteria Decision Analysis has been performed to prioritize the customer-selection criteria and customers with respect to selection criteria. Three experts with seven and three and ten years of experience have participated in the study. Findings of the study suggest large hospitals, large pharmacies, and small retail stores are the highly preferred customers. Moreover, findings of prioritization of customer-selection criteria from both Principal Component Analysis and Analytical Hierarchy Process are consistent. Furthermore, this study considers the experience of three experts to calculate an aggregate score of priorities to reach an effective decision. Unlike traditional supply chain problems of supplier selection, this study considers a selection of customers and is useful for procurement and supply chain managers to prioritize customers while considering multiple selection criteria. © 2021 Tech Science Press. All rights reserved.

Covidaroundus: Social distancing made easier

To reduce the dispersion of COVID - 19, people need to maintain safe distance from each other. This paper proposes a mobile application solution that keeps track of the COVID - 19 positive individuals in a certain area. With the help of the infected person's position uploaded in the cloud system, a location-based recommendation (i.e. informing people about a danger zone) is provided to the related users. Taking the pandemic into consideration, a proper visualization of users' location is made on the map using geospatial hotspot and location-based services. This paper describes the development of the mobile application that uses GPS data to pinpoint the infected person's location and create a danger zone based on the information. The accuracy of the services (provided by the application) was tested and confirmed through experiments. © 2021 IEEE.

Leveraging Convolutional Neural Network for COVID-19 Disease Detection Using CT Scan Images

In 2020, the world faced an unprecedented pandemic outbreak of coronavirus disease (COVID-19), which causes severe threats to patients suffering from diabetes, kidney problems, and heart problems. A rapid testing mechanism is a primary obstacle to controlling the spread of COVID-19. Current tests focus on the reverse transcription-polymerase chain reaction (RT-PCR). The PCR test takes around 4-6 h to identify COVID-19 patients. Various research has recommended AI-based models leveraging machine learning, deep learning, and neural networks to classify COVID-19 and non-COVID patients from chest X-ray and computerized tomography (CT) scan images. However, no model can be claimed as a standard since models use different datasets. Convolutional neural network (CNN)-based deep learning models are widely used for image analysis to diagnose and classify various diseases. In this research, we develop a CNN-based diagnostic model to detect COVID-19 patients by analyzing the features in CT scan images. This research considered a publicly available CT scan dataset and fed it into the proposed CNN model to classify COVID-19 infected patients. The model achieved 99.76%, 96.10%, and 96% accuracy in training, validation, and test phases, respectively. It achieved scores of 0.986 in area under curve (AUC) and 0.99 in the precision-recall curve (PRC). We compared the model's performance to that of three state-of-the-art pretrained models (MobileNetV2, InceptionV3, and Xception). The results show that the model can be used as a diagnostic tool for digital healthcare, particularly in COVID-19 chest CT image classification.

IoT-cloud based healthcare model for COVID-19 detection: an enhanced k-Nearest Neighbour classifier based approach

COVID - 19 affected severely worldwide. The pandemic has caused many causalities in a very short span. The IoT-cloud-based healthcare model requirement is utmost in this situation to provide a better decision in the covid-19 pandemic. In this paper, an attempt has been made to perform predictive analytics regarding the disease using a machine learning classifier. This research proposed an enhanced KNN (k NearestNeighbor) algorithm eKNN, which did not randomly choose the value of k. However, it used a mathematical function of the dataset's sample size while determining the k value. The enhanced KNN algorithm eKNN has experimented on 7 benchmark COVID-19 datasets of different size, which has been gathered from standard data cloud of different countries (Brazil, Mexico, etc.). It appeared that the enhanced KNN classifier performs significantly better than ordinary KNN. The second research question augmented the enhanced KNN algorithm with feature selection using ACO (Ant Colony Optimization). Results indicated that the enhanced KNN classifier along with the feature selection mechanism performed way better than enhanced KNN without feature selection. This paper involves proposing an improved KNN attempting to find an optimal value of k and studying IoT-cloud-based COVID - 19 detection.